English
Related papers

Related papers: Stateful Conformer with Cache-based Inference for …

200 papers

Non-autoregressive automatic speech recognition (NASR) models have gained attention due to their parallelism and fast inference. The encoder-based NASR, e.g. connectionist temporal classification (CTC), can be initialized from the speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Ruchao Fan , Natarajan Balaji Shanka , Abeer Alwan

Although the deep integration of the Automatic Speech Recognition (ASR) system with Large Language Models (LLMs) has significantly improved accuracy, the deployment of such systems in low-latency streaming scenarios remains challenging. In…

Sound · Computer Science 2026-03-13 Yinfeng Xia , Jian Tang , Junfeng Hou , Gaopeng Xu , Haitao Yao

Recurrent neural network transducer (RNN-T) is an end-to-end speech recognition framework converting input acoustic frames into a character sequence. The state-of-the-art encoder network for RNN-T is the Conformer, which can effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-20 Juntae Kim , Jeehye Lee

This paper proposes a non-autoregressive extension of our previously proposed sequence-to-sequence (S2S) model-based voice conversion (VC) methods. S2S model-based VC methods have attracted particular attention in recent years for their…

Sound · Computer Science 2021-04-15 Hirokazu Kameoka , Kou Tanaka , Takuhiro Kaneko

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Computation and Language · Computer Science 2020-11-20 Jay Mahadeokar , Yuan Shangguan , Duc Le , Gil Keren , Hang Su , Thong Le , Ching-Feng Yeh , Christian Fuegen , Michael L. Seltzer

Connectionist Temporal Classification (CTC) suffers from the latency problem when applied to streaming models. We argue that in CTC lattice, the alignments that can access more future context are preferred during training, thereby leading…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-22 Zengwei Yao , Wei Kang , Fangjun Kuang , Liyong Guo , Xiaoyu Yang , Yifan Yang , Long Lin , Daniel Povey

Recurrent Neural Network Transducer (RNN-T), like most end-to-end speech recognition model architectures, has an implicit neural network language model (NNLM) and cannot easily leverage unpaired text data during training. Previous work has…

Computation and Language · Computer Science 2020-10-28 Suyoun Kim , Yuan Shangguan , Jay Mahadeokar , Antoine Bruguier , Christian Fuegen , Michael L. Seltzer , Duc Le

Although end-to-end (E2E) automatic speech recognition (ASR) has shown state-of-the-art recognition accuracy, it tends to be implicitly biased towards the training data distribution which can degrade generalisation. This paper proposes a…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-28 Keqi Deng , Philip C. Woodland

Analyzing long text data such as customer call transcripts is a cost-intensive and tedious task. Machine learning methods, namely Transformers, are leveraged to model agent-customer interactions. Unfortunately, Transformers adhere to…

Computation and Language · Computer Science 2025-02-19 Annamalai Senthilnathan , Kristjan Arumae , Mohammed Khalilia , Zhengzheng Xing , Aaron R. Colak

We propose the Chunkwise Aligner, a novel architecture for streaming automatic speech recognition (ASR). While the Transducer is the standard model for streaming ASR, its training is costly due to the need to compute all possible…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-13 Wen Shen Teo , Takafumi Moriya , Masato Mimura

In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing…

Sound · Computer Science 2024-02-09 Sungho Jeon , Ching-Feng Yeh , Hakan Inan , Wei-Ning Hsu , Rashi Rungta , Yashar Mehdad , Daniel Bikel

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as quickly and accurately as possible, while full-context ASR waits for the completion of a full speech utterance before emitting completed hypotheses. In this…

Computation and Language · Computer Science 2021-01-28 Jiahui Yu , Wei Han , Anmol Gulati , Chung-Cheng Chiu , Bo Li , Tara N. Sainath , Yonghui Wu , Ruoming Pang

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

Image and Video Processing · Electrical Eng. & Systems 2024-02-28 A. Burakhan Koyuncu , Panqi Jia , Atanas Boev , Elena Alshina , Eckehard Steinbach

The unified streaming and non-streaming speech recognition model has achieved great success due to its comprehensive capabilities. In this paper, we propose to improve the accuracy of the unified model by bridging the inherent…

Computation and Language · Computer Science 2023-06-02 Yuting Yang , Yuke Li , Binbin Du

Automatic speech recognition (ASR) models make fewer errors when more surrounding speech information is presented as context. Unfortunately, acquiring a larger future context leads to higher latency. There exists an inevitable trade-off…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-21 Kwangyoun Kim , Felix Wu , Prashant Sridhar , Kyu J. Han , Shinji Watanabe

While large language models (LLMs) have been applied to automatic speech recognition (ASR), the task of making the model streamable remains a challenge. This paper proposes a novel model architecture, Transducer-Llama, that integrates LLMs…

Computation and Language · Computer Science 2024-12-24 Keqi Deng , Jinxi Guo , Yingyi Ma , Niko Moritz , Philip C. Woodland , Ozlem Kalinli , Mike Seltzer

This paper presents the use of non-autoregressive (NAR) approaches for joint automatic speech recognition (ASR) and spoken language understanding (SLU) tasks. The proposed NAR systems employ a Conformer encoder that applies connectionist…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-24 Mohan Li , Rama Doddipatla

Work on retrieval-based chatbots, like most sequence pair matching tasks, can be divided into Cross-encoders that perform word matching over the pair, and Bi-encoders that encode the pair separately. The latter has better performance,…

Computation and Language · Computer Science 2019-11-07 Amir Vakili Tahami , Azadeh Shakery

For most of the attention-based sequence-to-sequence models, the decoder predicts the output sequence conditioned on the entire input sequence processed by the encoder. The asynchronous problem between the encoding and decoding makes these…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-25 Zhengkun Tian , Jiangyan Yi , Ye Bai , Jianhua Tao , Shuai Zhang , Zhengqi Wen

End-to-end models are favored in automatic speech recognition (ASR) because of its simplified system structure and superior performance. Among these models, recurrent neural network transducer (RNN-T) has achieved significant progress in…

Sound · Computer Science 2020-11-18 Xiong Wang , Zhuoyuan Yao , Xian Shi , Lei Xie